ui-review
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses standard diagnostic tools (Read, Grep, Glob) to perform static analysis on UI code according to a provided checklist. It does not perform any network operations, credential access, or command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external files, creating a potential surface for indirect prompt injection. 1. Ingestion point: File contents read from $ARGUMENTS in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Read-only access using Read, Grep, and Glob tools. 4. Sanitization: Absent. The risk is assessed as safe/low as the agent lacks tools to execute commands or exfiltrate data.
Audit Metadata